14 January 2019 in IEEE Transactions on Image Processing
Cross-camera label estimation from a set of unlabeled training data is an extremely important component in the unsupervised person re-identification (re-ID) systems. With the estimated labels, the existing advanced supervised learning methods can be leveraged to learn discriminative re-ID models. In this paper, we utilize the graph matching technique for accurate label estimation due to its advantages in optimal global matching and intra-camera relationship mining. However, the graph structure constructed with non-learned similarity measurement cannot handle the large cross-camera variations, which leads to noisy and inaccurate label outputs. This paper designs a dynamic graph matching (DGM) framework, which improves the label estimation process by iteratively refining the graph structure with better similarity measurement learned from the intermediate estimated labels. In addition, we design a positive re-weighting strategy to refine the intermediate labels, which enhances the robustness against inaccurate matching output and noisy initial training data. To fully utilize the abundant video information and reduce false matchings, a co-matching strategy is further incorporated into the framework. Comprehensive experiments conducted on three video benchmarks demonstrate that DGM outperforms the state-of-the-art unsupervised re-ID methods and yields the competitive performance to fully supervised upper bounds.
27 March 2018 in International Journal of Computer Vision
27 September 2017 in arXiv
Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models. Specifically, we propose to construct a graph for samples in each camera, and then graph matching scheme is introduced for cross-camera labeling association. While labels directly output from existing graph matching methods may be noisy and inaccurate due to significant cross-camera variations, this paper proposes a dynamic graph matching (DGM) method. DGM iteratively updates the image graph and the label estimation process by learning a better feature space with intermediate estimated labels. DGM is advantageous in two aspects: 1) the accuracy of estimated labels is improved significantly with the iterations; 2) DGM is robust to noisy initial training data. Extensive experiments conducted on three benchmarks including the large-scale MARS dataset show that DGM yields competitive performance to fully supervised baselines, and outperforms competing unsupervised learning methods.
1 January 2019 in The Electronic Journal of Linear Algebra
In this paper, some inequalities for permanents and permanental minors of row substochastic matrices are proved. The convexity of the permanent function on the interval between the identity matrix and an arbitrary row substochastic matrix is also proved. In addition, a conjecture about the permanent and permanental minors of square row substochastic matrices with fixed row and column sums is formulated.